Study on the influence of region of interest on the detection of total sugar content in apple using hyperspectral imaging technology

MA, Xueting; Luo, Huiyang; ZHANG, Fei; GAO, Feng

doi:10.1590/fst.87922

Cited by 8 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Successive projections algorithm (SPA) is a forward feature variable selection method, that can find the most representative characteristic wavebands by analyzing collinearity between bands (Ma et al, 2022). The genetic algorithm (GA) is a method of searching for an optimal solution by simulating the natural evolution process (Wan et al, 2021).…”

Section: Optimal Wavelength Selectionmentioning

confidence: 99%

Hyperspectral image-based measurement of total flavonoid content of leaf-use Ginkgo biloba L.

et al. 2023

View full text Add to dashboard Cite

Ginkgo biloba leaf is a kind of food raw material with high concentration of total flavonoid content (TFC). Since conventional measurements of TFC are time-consuming and destructive, the approach of hyperspectral imaging-based prediction was investigated in this study. Hyperspectral images were collected in visual near-infrared (VIS-NIR) and short-wave near-infrared (SW-NIR). Initial comparative analysis on the full spans of the two wavelengths using partial least squares regression (PLSR) and support vector regression (SVR) showed that the TFC of the leaves could be barely captured only when PLSR working on short-wave infrared, with 2 p R and p RMSE on testing set being respectively 0.5496 and 0.6384 mg/g. To further improve prediction performance meeting industrial requirements, another comparative study on feature selection was conducted to fine-tune the PLSR on SW-NIR using a genetic algorithm (GA) and successive projections algorithm (SPA). Results showed that GA-PLSR with 50 characteristic wavelengths mostly from the ranges of 1100-1200 nm and 1400-1500 nm had a significant improvement in performance, giving 0.8482 and 0.2967 mg/g for 2 p R and p RMSE , respectively. Therefore, an approach, GA-PLSR modeling on SW-NIR hyperspectral images, was established for the ginkgo leaves industry to rapidly and non-invasively predict the leaf concentration from the total flavonoid of ginkgo biloba seedling leaf.

show abstract

Section: Optimal Wavelength Selectionmentioning

confidence: 99%

Hyperspectral image-based measurement of total flavonoid content of leaf-use Ginkgo biloba L.

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The total sugar content of fruits was based on the anthrone colorimetric method [32]. We mixed 1.25 mL of fruit juice with 2.5 mL of anthrone reagent for 15 min at 10-15 • C and another 15 min at 100 • C. Afterward, it was cooled for 1 h at room temperature so that the color could develop.…”

Section: Total Sugarsmentioning

confidence: 99%

The Effects of Low-Input (Wild and Organic Farming) Conditions on the Nutritional Profile of Ziziphus jujuba Mill. Fruits from the Valencian Mediterranean

Fukalova Fukalova,

García-Martínez,

Esteve Ciudad

et al. 2023

Sustainability

View full text Add to dashboard Cite

Jujube fruit (Ziziphus jujuba Mill.) has been a food source since ancient times. In Spain, it is considered a marginal crop, and jujube fruits are of low economic importance. Its consumption is bound to local marketplaces. However, jujube is a good alternative crop due to its climatic adaptation and low-input conditions. We aimed to evaluate the morphological, physicochemical, and bioactive compounds of jujube fruits grown under low-input conditions (wild and organic farming) in the Mediterranean basin, specifically in Marjal de los Moros, Valencia, Spain. The organic system produces higher protein, fiber, ash, and carbohydrate concentrations from small-caliber fruit cultivars. Potassium and phosphorus are the major mineral elements in jujube. The fruits’ total polyphenols range from 480.83 to 630.81 mg EGA·100 g−1 fw in organic conditions and 520.71 mg EGA·100 g−1 fw in wild conditions. Low-input conditions influence the production of glucose (sweet fruits) and bioactive compounds, as well as mineral concentrations. A strong relationship exists between vitamin C levels and the potassium concentration. Jujube fruits are classified as “vitamin C-rich”. A 20 g serving of fruit can provide the regular vitamin C requirements of an adult person. The environmental and nutritional opportunities offered by jujubes are in line with different SDGs.

show abstract

“…Related studies have investigated the impact of selection methods for ROIs based on hyperspectral imaging techniques on the detection results of total sugar in apples. 12 Deng et al proposed a PLSR model combined with a three-dimensional Gabor filter to predict the moisture content of Longjing tea based on NIR hyperspectral imaging. 13 Hyperspectral images of dried mangoes were acquired and used three band selection strategies.…”

Section: Introductionmentioning

confidence: 99%

“…The spectra of regions of interest (ROIs) in hyperspectral images are the source of data, and a crucial step in predicting the moisture content of semen ziziphi spinosae based on hyperspectral technology, it directly affects the accuracy and stability of qualitative or quantitative analysis models. Related studies have investigated the impact of selection methods for ROIs based on hyperspectral imaging techniques on the detection results of total sugar in apples 12 . Deng et al proposed a PLSR model combined with a three‐dimensional Gabor filter to predict the moisture content of Longjing tea based on NIR hyperspectral imaging 13 .…”

Section: Introductionmentioning

confidence: 99%

Moisture content prediction of semen ziziphi spinosae based on hyperspectral images coupled with convolutional neural networks and subregional voting

Liu

et al. 2023

Journal of Chemometrics

View full text Add to dashboard Cite

Deep learning algorithms represented by convolutional neural networks bring new opportunities for spectral analysis technology. Convolutional neural networks are more straightforward than traditional chemometric algorithms for detecting the quality of agricultural products, reducing the procedures of spectral preprocessing and band selection, and with higher prediction accuracy. However, there are few research papers on the relevance of the explanation of the convolutional neural networks model mechanism, and the reader cannot fully understand convolutional neural networks feature learning. In this study, convolutional neural networks combined with the subregional voting method were used to predict the moisture content of semen ziziphi spinosae. Firstly, 10 regions of interest were divided using the subregional voting method, and the results of network models were compared. It was found that the average spectrum of the fifth region of interest had the best prediction of moisture content because it was closest to the central region of semen ziziphi spinosae. Based on this, a convolutional neural network containing three convolutional layers, three pooling layers, and one fully connected layer is proposed. Partial least squares regression, backpropagation neural network, and convolutional neural networks were established to predict the moisture content of semen ziziphi spinosae. The correlation coefficient of the prediction set of the partial least squares regression is 0.98 after the multiplicative scatter correction preprocessed the spectra, and correlation coefficient of the prediction set of the backpropagation neural network is 0.83 after the standard normal variate preprocessed the spectra. The correlation coefficient of the prediction set of the convolutional neural networks established by using the raw spectra reached 0.99. The spectral preprocessing method can improve the prediction set correlation coefficient of partial least squares regression and backpropagation neural network. Still, it will reduce the prediction ability of convolutional neural networks. This study also analyzed the effect of different learning rates on the performance of convolutional neural networks, and it was found that the training loss and training accuracy performed most consistently when the learning rate was 0.01. Secondly, this study also visualized the output feature maps of the three convolutional layers of convolutional neural networks and verified the effectiveness of convolutional neural networks feature band extraction. This study provides new ideas for deep learning in the online detection of seed moisture content.

show abstract

Study on the influence of region of interest on the detection of total sugar content in apple using hyperspectral imaging technology

Cited by 8 publications

References 25 publications

Hyperspectral image-based measurement of total flavonoid content of leaf-use Ginkgo biloba L.

Hyperspectral image-based measurement of total flavonoid content of leaf-use Ginkgo biloba L.

The Effects of Low-Input (Wild and Organic Farming) Conditions on the Nutritional Profile of Ziziphus jujuba Mill. Fruits from the Valencian Mediterranean

Moisture content prediction of semen ziziphi spinosae based on hyperspectral images coupled with convolutional neural networks and subregional voting

Contact Info

Product

Resources

About